Github user gatorsmile commented on a diff in the pull request:
https://github.com/apache/spark/pull/21857#discussion_r205554196
--- Diff: sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala ---
@@ -1947,6 +1947,21 @@ class Dataset[T] private[sql](
Except(planWithBarrier, other.planWithBarrier)
}
+ /**
+ * Returns a new Dataset containing rows in this Dataset but not in
another Dataset while
+ * preserving the duplicates.
+ * This is equivalent to `EXCEPT ALL` in SQL.
+ *
+ * @note Equality checking is performed directly on the encoded
representation of the data
+ * and thus is not affected by a custom `equals` function defined on `T`.
+ *
+ * @group typedrel
+ * @since 2.4.0
+ */
+ def exceptAll(other: Dataset[T]): Dataset[T] = withSetOperator {
+ Except(planWithBarrier, other.planWithBarrier, true)
--- End diff --
isAll = true
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
